setwd("~/Documents/GitHub/Resultados/docs/PrimeroDiffExpAllResults/Clasificando/Abundances")
load('CheackPointOne.RData')

Primera Clasificacion: pEhEx

head(pEhExvsCmasM,10);
##          GenId    CDC5_1     CDC5_2    CDC5_3    pEhEx_1    pEhEx_2    pEhEx_3
## 1  EHI_000130A  45.32378  107.82734 128.66351  180.07428  446.15729  516.14317
## 2  EHI_000140A  66.04322  317.74653 257.32703  363.20067  351.59134   41.84945
## 3  EHI_000240A 700.57610 1282.45711 877.45524 1208.63415 1993.15918 2290.09468
## 4  EHI_000250A 707.05093  430.16227 388.98271  334.20566  337.04273  710.66559
## 5  EHI_000260A  94.53245  108.97444  35.15805  112.16491   69.10588   54.24928
## 6  EHI_000280A  58.27343   50.47237  80.78872   56.46397   86.07926   66.64912
## 7  EHI_000290A  27.19427   14.91229  23.93740   19.07567   14.54861   87.57384
## 8  EHI_000300A  60.86336  143.38742 110.71046  137.34479  118.81363   34.09955
## 9  EHI_000410A  15.53958   21.79489  23.18935   28.99501   25.46006   70.52407
## 10 EHI_000430A  27.19427   27.53039  22.44131   26.70593   14.54861   11.62485
nbreaks <- 10
data1 <- pEhExvsCDC5;       head(data1)
##         GenId    CDC5_1    CDC5_2     CDC5_3    pEhEx_1    pEhEx_2    pEhEx_3
## 1 EHI_000130A  72.59485  40.99764  280.54541  169.92967  411.34855  466.86626
## 2 EHI_000140A 111.02742 145.24877  643.77044  342.73950  324.16054   37.85402
## 3 EHI_000240A 876.83189 752.01378 1122.88829 1140.54489 1837.65493 2071.45616
## 4 EHI_000250A 492.50623 510.71341  232.49229  315.37794  310.74700  642.81736
## 5 EHI_000260A  12.81086 107.76521    2.11999  105.84602   63.71431   49.07003
## 6 EHI_000280A  58.36056  42.16900  171.71923   53.28303   79.36344   60.28603

Log-NormalizaciĂ³n

sample1   <- data1$pEhEx_1; sample2   <- data1$pEhEx_2; sample3   <- data1$pEhEx_3;
samplevs1 <- data1$CDC5_1;  samplevs2 <- data1$CDC5_2;  samplevs3 <- data1$CDC5_3;
log2sample1 <- log2(sample1+1);         log2sample2 <- log2(sample2+1)
log2sample3 <- log2(sample3+1);         log2samplevsCDC51 <- log2(samplevs1+1)
log2samplevsCDC52 <- log2(samplevs2+1); log2samplevsCDC53 <- log2(samplevs3+1)
data1 <- cbind(data1, log2sample1,log2sample2,log2sample3,
               log2samplevsCDC51,log2samplevsCDC52,log2samplevsCDC53)
head(data1)
##         GenId    CDC5_1    CDC5_2     CDC5_3    pEhEx_1    pEhEx_2    pEhEx_3
## 1 EHI_000130A  72.59485  40.99764  280.54541  169.92967  411.34855  466.86626
## 2 EHI_000140A 111.02742 145.24877  643.77044  342.73950  324.16054   37.85402
## 3 EHI_000240A 876.83189 752.01378 1122.88829 1140.54489 1837.65493 2071.45616
## 4 EHI_000250A 492.50623 510.71341  232.49229  315.37794  310.74700  642.81736
## 5 EHI_000260A  12.81086 107.76521    2.11999  105.84602   63.71431   49.07003
## 6 EHI_000280A  58.36056  42.16900  171.71923   53.28303   79.36344   60.28603
##   log2sample1 log2sample2 log2sample3 log2samplevsCDC51 log2samplevsCDC52
## 1    7.417259    8.687721    8.869952          6.201533          5.392236
## 2    8.425172    8.345008    5.279992          6.807708          7.192281
## 3   10.156772   10.844435   11.017126          9.777801          9.556532
## 4    8.305505    8.284232    9.330508          8.946924          8.999192
## 5    6.739389    6.016013    5.645875          3.787731          6.765073
## 6    5.762429    6.328467    5.937486          5.891433          5.431924
##   log2samplevsCDC53
## 1          8.137224
## 2          9.332642
## 3         10.134283
## 4          7.867231
## 5          1.641542
## 6          7.432285
save.image('CheckPointTwo.RData')
setwd("~/Documents/GitHub/Resultados/docs/PrimeroDiffExpAllResults/Clasificando/Abundances")
#load('CheckPointTwo.RData')
library(ggplot2);library(dplyr);library("fitdistrplus");
## 
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
## 
##     filter, lag
## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union
## Loading required package: MASS
## 
## Attaching package: 'MASS'
## The following object is masked from 'package:dplyr':
## 
##     select
## Loading required package: survival
library("MASS");library("survival")
head(data1)
##         GenId    CDC5_1    CDC5_2     CDC5_3    pEhEx_1    pEhEx_2    pEhEx_3
## 1 EHI_000130A  72.59485  40.99764  280.54541  169.92967  411.34855  466.86626
## 2 EHI_000140A 111.02742 145.24877  643.77044  342.73950  324.16054   37.85402
## 3 EHI_000240A 876.83189 752.01378 1122.88829 1140.54489 1837.65493 2071.45616
## 4 EHI_000250A 492.50623 510.71341  232.49229  315.37794  310.74700  642.81736
## 5 EHI_000260A  12.81086 107.76521    2.11999  105.84602   63.71431   49.07003
## 6 EHI_000280A  58.36056  42.16900  171.71923   53.28303   79.36344   60.28603
##   log2sample1 log2sample2 log2sample3 log2samplevsCDC51 log2samplevsCDC52
## 1    7.417259    8.687721    8.869952          6.201533          5.392236
## 2    8.425172    8.345008    5.279992          6.807708          7.192281
## 3   10.156772   10.844435   11.017126          9.777801          9.556532
## 4    8.305505    8.284232    9.330508          8.946924          8.999192
## 5    6.739389    6.016013    5.645875          3.787731          6.765073
## 6    5.762429    6.328467    5.937486          5.891433          5.431924
##   log2samplevsCDC53
## 1          8.137224
## 2          9.332642
## 3         10.134283
## 4          7.867231
## 5          1.641542
## 6          7.432285

Muestra 1

log2sample1 <- data1$log2sample1; head(mean(log2sample1)); head(sd(log2sample1))
## [1] 6.30237
## [1] 2.868113
head(log2sample1,5)
## [1]  7.417259  8.425172 10.156772  8.305505  6.739389
summary(data1)
##     GenId               CDC5_1              CDC5_2              CDC5_3        
##  Length:4772        Min.   :     0.00   Min.   :     0.00   Min.   :     0.0  
##  Class :character   1st Qu.:    17.08   1st Qu.:    17.57   1st Qu.:    16.3  
##  Mode  :character   Median :    45.55   Median :    49.20   Median :    44.5  
##                     Mean   :  1749.28   Mean   :  1748.01   Mean   :  1980.0  
##                     3rd Qu.:   196.79   3rd Qu.:   208.50   3rd Qu.:   177.4  
##                     Max.   :270953.87   Max.   :270338.41   Max.   :481876.0  
##     pEhEx_1            pEhEx_2             pEhEx_3          log2sample1    
##  Min.   :     0.0   Min.   :     0.00   Min.   :     0.0   Min.   : 0.000  
##  1st Qu.:    18.0   1st Qu.:    15.65   1st Qu.:    15.4   1st Qu.: 4.248  
##  Median :    50.4   Median :    49.18   Median :    54.0   Median : 5.684  
##  Mean   :  1395.0   Mean   :  1717.64   Mean   :  1909.2   Mean   : 6.302  
##  3rd Qu.:   208.1   3rd Qu.:   223.84   3rd Qu.:   242.0   3rd Qu.: 7.708  
##  Max.   :207266.7   Max.   :265749.05   Max.   :707261.7   Max.   :17.661  
##   log2sample2      log2sample3     log2samplevsCDC51 log2samplevsCDC52
##  Min.   : 0.000   Min.   : 0.000   Min.   : 0.000    Min.   : 0.000   
##  1st Qu.: 4.057   1st Qu.: 4.038   1st Qu.: 4.176    1st Qu.: 4.215   
##  Median : 5.649   Median : 5.781   Median : 5.541    Median : 5.650   
##  Mean   : 6.237   Mean   : 6.186   Mean   : 6.244    Mean   : 6.270   
##  3rd Qu.: 7.813   3rd Qu.: 7.925   3rd Qu.: 7.628    3rd Qu.: 7.711   
##  Max.   :18.020   Max.   :19.432   Max.   :18.048    Max.   :18.044   
##  log2samplevsCDC53
##  Min.   : 0.000   
##  1st Qu.: 4.109   
##  Median : 5.508   
##  Mean   : 6.114   
##  3rd Qu.: 7.479   
##  Max.   :18.878
ndata1    <- length(log2sample1)
hist(log2sample1, breaks = nbreaks, col= rainbow(25,0.3), 
     main = 'Log2 sample1')

meanlog2sample1 <- mean(log2sample1); head(meanlog2sample1)
## [1] 6.30237
StdDevlog2sample1 <- sd(log2sample1); head(StdDevlog2sample1)
## [1] 2.868113
Normlog2sample1 <- (log2sample1-meanlog2sample1)/StdDevlog2sample1; head(Normlog2sample1)
## [1]  0.3887185  0.7401387  1.3438805  0.6984156  0.1523717 -0.1882564
tst<- Normlog2sample1

hist(tst, breaks = nbreaks, col= 1:5, 
     main = 'Normalized Log2sample1',
     xlab='pEhEx1',
     ylab= 'Frequency pEhEx')

fw1<-fitdist(tst, "norm")
plotdist(tst, histo = TRUE, demp = TRUE)

nnorm.f <- fitdist(tst,"norm")
summary(nnorm.f)
## Fitting of the distribution ' norm ' by maximum likelihood 
## Parameters : 
##           estimate Std. Error
## mean -9.053474e-17 0.01447452
## sd    9.998952e-01 0.01023499
## Loglikelihood:  -6770.675   AIC:  13545.35   BIC:  13558.29 
## Correlation matrix:
##      mean sd
## mean    1  0
## sd      0  1
par(mfrow=c(2,2))
denscomp(nnorm.f,legendtext = 'Dist Normal')
qqcomp(nnorm.f,legendtext = 'Dist Normal')
cdfcomp(nnorm.f,legendtext = 'Dist Normal')
ppcomp(nnorm.f,legendtext = 'Dist Normal')

probs <- c();
probs[8] = 0.175;  probs[9] = 0.825; 
probs[7] = 0.15;   probs[10] = 0.85;   
probs[6] = 0.125;  probs[11] = 0.875; 
probs[5] = 0.1;    probs[12] = 0.9;    
probs[4] = 0.075;  probs[13] = 0.925; 
probs[3] = 0.05;   probs[14] = 0.95;   
probs[2] = 0.025;  probs[15] = 0.975; 
probs[1] = 0.005;  probs[16] = 0.995;  
CuantilesData <- quantile(tst,prob = probs)
CuantilesModel <- qnorm(probs, mean=0, sd=1)
Cuantilillos <- t(CuantilesModel)
colnames(Cuantilillos) <- c('0.5%','2.5%','5%','7.5%',
                            '10%','12.5%','15%','17.5%',
                            '82.5%','85%','87.5%','90%',
                            '92.5%','95%','97.5%','99.5%')
Cuantilillos <- t(Cuantilillos)
colnames(Cuantilillos) <- c('Cuantiles Ajuste')
print(Cuantilillos)
##       Cuantiles Ajuste
## 0.5%        -2.5758293
## 2.5%        -1.9599640
## 5%          -1.6448536
## 7.5%        -1.4395315
## 10%         -1.2815516
## 12.5%       -1.1503494
## 15%         -1.0364334
## 17.5%       -0.9345893
## 82.5%        0.9345893
## 85%          1.0364334
## 87.5%        1.1503494
## 90%          1.2815516
## 92.5%        1.4395315
## 95%          1.6448536
## 97.5%        1.9599640
## 99.5%        2.5758293

CĂ¡lculo de cuantiles

CuantilesA <- matrix(0,8,2)
CuantilesD <- matrix(0,8,2)
colnames(CuantilesA) <- c('LimInf','LimSup')
colnames(CuantilesD) <- c('LimInf','LimSup')
rownames(CuantilesA) <- c('65','70','75','80','85','90','95','99')
rownames(CuantilesD) <- c('65','70','75','80','85','90','95','99')
CuantilesA[1,1] <-CuantilesData[8]; CuantilesA[1,2] <-CuantilesData[9]
CuantilesA[2,1] <-CuantilesData[7]; CuantilesA[2,2] <-CuantilesData[10]
CuantilesA[3,1] <-CuantilesData[6]; CuantilesA[3,2] <-CuantilesData[11]
CuantilesA[4,1] <-CuantilesData[5]; CuantilesA[4,2] <-CuantilesData[12]
CuantilesA[5,1] <-CuantilesData[4]; CuantilesA[5,2] <-CuantilesData[13]
CuantilesA[6,1] <-CuantilesData[3]; CuantilesA[6,2] <-CuantilesData[14]
CuantilesA[7,1] <-CuantilesData[2]; CuantilesA[7,2] <-CuantilesData[15]
CuantilesA[8,1] <-CuantilesData[1]; CuantilesA[8,2] <-CuantilesData[16]
CuantilesD[1,1] <-Cuantilillos[8];  CuantilesD[1,2] <-Cuantilillos[9]
CuantilesD[2,1] <-Cuantilillos[7];  CuantilesD[2,2] <-Cuantilillos[10]
CuantilesD[3,1] <-Cuantilillos[6];  CuantilesD[3,2] <-Cuantilillos[11]
CuantilesD[4,1] <-Cuantilillos[5];  CuantilesD[4,2] <-Cuantilillos[12]
CuantilesD[5,1] <-Cuantilillos[4];  CuantilesD[5,2] <-Cuantilillos[13]
CuantilesD[6,1] <-Cuantilillos[3];  CuantilesD[6,2] <-Cuantilillos[14]
CuantilesD[7,1] <-Cuantilillos[2];  CuantilesD[7,2] <-Cuantilillos[15]
CuantilesD[8,1] <-Cuantilillos[1];  CuantilesD[8,2] <-Cuantilillos[16]
print(CuantilesD)
##        LimInf    LimSup
## 65 -0.9345893 0.9345893
## 70 -1.0364334 1.0364334
## 75 -1.1503494 1.1503494
## 80 -1.2815516 1.2815516
## 85 -1.4395315 1.4395315
## 90 -1.6448536 1.6448536
## 95 -1.9599640 1.9599640
## 99 -2.5758293 2.5758293
print(CuantilesA)
##        LimInf    LimSup
## 65 -0.8713278 0.8126272
## 70 -0.9260903 0.9617987
## 75 -0.9875514 1.1301158
## 80 -1.0213487 1.3734820
## 85 -1.0966280 1.6988689
## 90 -1.1851905 2.1819106
## 95 -1.3565981 2.6079805
## 99 -1.9245847 3.1666752
col_sequence <- rainbow(n = 7, alpha = 0.35, start = 0, end = 1)
par(mfrow=c(2,1))
hist(tst, breaks = nbreaks, col = col_sequence,
     main = 'Normalized Log2 pEhEx - DATA', lty = 9)

abline(v=CuantilesA[1,1], lty=2, col="darkgoldenrod4"); # 65% INFERIOR
abline(v=CuantilesA[1,2], lty=2, col="darkgoldenrod4"); # 65% SUPERIOR
abline(v=CuantilesA[2,1], lty=2, col="darkblue"); # 70% INFERIOR
abline(v=CuantilesA[2,2], lty=2, col="darkblue") # 70% SUPERIOR
abline(v=CuantilesA[3,1], lty=2, col="aquamarine4"); # 75% INFERIOR
abline(v=CuantilesA[3,2], lty=2, col="aquamarine4"); # 75% SUPERIOR
abline(v=CuantilesA[4,1], lty=2, col="green");  # 80% INFERIOR
abline(v=CuantilesA[4,2], lty=2, col="green"); # 80% SUPERIOR
abline(v=CuantilesA[5,1], lty=2, col="brown"); # 85% INFERIOR
abline(v=CuantilesA[5,2], lty=2, col="brown"); # 85% SUPERIOR
abline(v=CuantilesA[6,1], lty=2, col="red");  # 90% INFERIOR
abline(v=CuantilesA[6,2], lty=2, col="red"); # 90% SUPERIOR
abline(v=CuantilesA[7,1], lty=2, col="blue");  # 95% INFERIOR
abline(v=CuantilesA[7,2], lty=2, col="blue"); # 95% SUPERIOR
abline(v=CuantilesA[8,1], lty=2, col="orange");  # 99% INFERIOR
abline(v=CuantilesA[8,2], lty=2, col="orange"); # 99% SUPERIOR
legend("topright",
       legend=c("65%","70%","75%","80%","85%","90%","95%","99%"), 
       pch=c(1,2,3,4,5,6,7,8),
       col=c("darkgoldenrod4","darkblue","aquamarine4",
             "green", "brown","red","blue","orange"))
hist(tst, breaks = nbreaks, col = col_sequence,
     main = 'Normalized Log2   pEhEx - ADJUSTED', lty=9)
abline(v=CuantilesD[1,1], lty=2, col="darkgoldenrod4"); # 65% INFERIOR
abline(v=CuantilesD[1,2], lty=2, col="darkgoldenrod4"); # 65% SUPERIOR
abline(v=CuantilesD[2,1], lty=2, col="darkblue");  # 70% INFERIOR
abline(v=CuantilesD[2,2], lty=2, col="darkblue"); # 70% SUPERIOR
abline(v=CuantilesD[3,1], lty=2, col="aquamarine4");  # 75% INFERIOR
abline(v=CuantilesD[3,2], lty=2, col="aquamarine4"); # 75% SUPERIOR
abline(v=CuantilesD[4,1], lty=2, col="green");  # 80% INFERIOR
abline(v=CuantilesD[4,2], lty=2, col="green"); # 80% SUPERIOR
abline(v=CuantilesD[5,1], lty=2, col="brown");  # 85% INFERIOR
abline(v=CuantilesD[5,2], lty=2, col="brown"); # 85% SUPERIOR
abline(v=CuantilesD[6,1], lty=2, col="red");  # 90% INFERIOR
abline(v=CuantilesD[6,2], lty=2, col="red"); # 90% SUPERIOR
abline(v=CuantilesD[7,1], lty=2, col="blue");  # 95% INFERIOR
abline(v=CuantilesD[7,2], lty=2, col="blue"); # 95% SUPERIOR
abline(v=CuantilesD[8,1], lty=2, col="orange");  # 99% INFERIOR
abline(v=CuantilesD[8,2], lty=2, col="orange"); # 99% SUPERIOR
legend("topright",
       legend=c("65%","70%","75%","80%","85%","90%","95%","99%"), 
       pch=c(1,2,3,4,5,6,7,8),
       col=c("darkgoldenrod4","darkblue","aquamarine4",
             "green", "brown","red","blue","orange"))

Grafica Cuantiles del \(65\%\) y \(80\%\)

par(mfrow=c(2,1))
hist(tst, breaks = nbreaks, col = col_sequence,
     main = 'Normalized Log2  pEhEx - DATA', lty=9)

abline(v=CuantilesA[1,1], lty=2, col="darkgoldenrod4"); # 65% INFERIOR
abline(v=CuantilesA[1,2], lty=2, col="darkgoldenrod4"); # 65% SUPERIOR
abline(v=CuantilesA[4,1], lty=2, col="green");  # 80% INFERIOR
abline(v=CuantilesA[4,2], lty=2, col="green"); # 80% SUPERIOR
legend("topright",legend=c("65%","80%"), 
       pch=c(1,2),col=c("darkgoldenrod4","green"))
hist(tst, breaks = nbreaks, col = col_sequence,
     main = 'Normalized Log2  BaseMean - ADJUSTED', lty=9)

abline(v=CuantilesD[1,1], lty=2, col="darkgoldenrod4"); # 65% INFERIOR
abline(v=CuantilesD[1,2], lty=2, col="darkgoldenrod4"); # 65% SUPERIOR
abline(v=CuantilesD[4,1], lty=2, col="green");  # 80% INFERIOR
abline(v=CuantilesD[4,2], lty=2, col="green"); # 80% SUPERIOR
legend("topright",legend=c("65%","80%"), 
       pch=c(1,2),col=c("darkgoldenrod4","green"))

Grafica Cuantiles del \(70\%\) y \(85\%\)

par(mfrow=c(2,1))
hist(tst, breaks = nbreaks, col = col_sequence, 
     main = 'Normalized Log2 pEhEx - DATA', lty=9)

abline(v=CuantilesA[2,1], lty=2, col="darkblue"); 
abline(v=CuantilesA[2,2], lty=2, col="darkblue")
abline(v=CuantilesA[5,1], lty=2, col="brown"); 
abline(v=CuantilesA[5,2], lty=2, col="brown")
legend("topright",legend=c("70%","85%"),
       pch=c(1,2),#3,4,5,6,7,8),
       col=c("brown"))
hist(tst, breaks = nbreaks, col = col_sequence,
     main = 'Normalized Log2  pEhEx - ADJUSTED', lty=9)

abline(v=CuantilesD[2,1], lty=2, col="darkblue"); 
abline(v=CuantilesD[2,2], lty=2, col="darkblue")
abline(v=CuantilesD[5,1], lty=2, col="brown"); 
abline(v=CuantilesD[5,2], lty=2, col="brown")
legend("topright",legend=c("70%","85%"),
       pch=c(1,2),#3,4,5,6,7,8),
       col=c("brown"))

Muestra 2

log2sample2 <- data1$log2sample2; head(mean(log2sample2)); head(sd(log2sample2))
## [1] 6.237216
## [1] 3.103083
head(log2sample2,5)
## [1]  8.687721  8.345008 10.844435  8.284232  6.016013
ndata1    <- length(log2sample2)
hist(log2sample2, breaks = nbreaks, col= rainbow(25,0.3), 
     main = 'Log2 sample2')

Log-normalizacion

meanlog2sample2 <- mean(log2sample2); head(meanlog2sample2)
## [1] 6.237216
StdDevlog2sample2 <- sd(log2sample2); head(StdDevlog2sample2)
## [1] 3.103083
Normlog2sample2 <- (log2sample2-meanlog2sample2)/StdDevlog2sample2; head(Normlog2sample2)
## [1]  0.78969998  0.67925752  1.48472313  0.65967167 -0.07128491  0.02940674
tst<- Normlog2sample2
hist(tst, breaks = nbreaks, col= 1:5, 
     main = 'Normalized Log2sample1',
     xlab='pEhEx1',
     ylab= 'Frequency pEhEx')

Ajuste de modelo

fw1<-fitdist(tst, "norm")
plotdist(tst, histo = TRUE, demp = TRUE)

nnorm.f <- fitdist(tst,"norm")
summary(nnorm.f)
## Fitting of the distribution ' norm ' by maximum likelihood 
## Parameters : 
##           estimate Std. Error
## mean -1.260395e-16 0.01447452
## sd    9.998952e-01 0.01023499
## Loglikelihood:  -6770.675   AIC:  13545.35   BIC:  13558.29 
## Correlation matrix:
##      mean sd
## mean    1  0
## sd      0  1
par(mfrow=c(2,2))
denscomp(nnorm.f,legendtext = 'Dist Normal')
qqcomp(nnorm.f,legendtext = 'Dist Normal')
cdfcomp(nnorm.f,legendtext = 'Dist Normal')
ppcomp(nnorm.f,legendtext = 'Dist Normal')

probs <- c();
probs[8] = 0.175;  probs[9] = 0.825; 
probs[7] = 0.15;   probs[10] = 0.85;   
probs[6] = 0.125;  probs[11] = 0.875; 
probs[5] = 0.1;    probs[12] = 0.9;    
probs[4] = 0.075;  probs[13] = 0.925; 
probs[3] = 0.05;   probs[14] = 0.95;   
probs[2] = 0.025;  probs[15] = 0.975; 
probs[1] = 0.005;  probs[16] = 0.995;  
CuantilesData <- quantile(tst,prob = probs)
CuantilesModel <- qnorm(probs, mean=0, sd=1)
Cuantilillos <- t(CuantilesModel)
colnames(Cuantilillos) <- c('0.5%','2.5%','5%','7.5%',
                            '10%','12.5%','15%','17.5%',
                            '82.5%','85%','87.5%','90%',
                            '92.5%','95%','97.5%','99.5%')
Cuantilillos <- t(Cuantilillos)
colnames(Cuantilillos) <- c('Cuantiles Ajuste')
print(Cuantilillos)
##       Cuantiles Ajuste
## 0.5%        -2.5758293
## 2.5%        -1.9599640
## 5%          -1.6448536
## 7.5%        -1.4395315
## 10%         -1.2815516
## 12.5%       -1.1503494
## 15%         -1.0364334
## 17.5%       -0.9345893
## 82.5%        0.9345893
## 85%          1.0364334
## 87.5%        1.1503494
## 90%          1.2815516
## 92.5%        1.4395315
## 95%          1.6448536
## 97.5%        1.9599640
## 99.5%        2.5758293
CuantilesA <- matrix(0,8,2)
CuantilesD <- matrix(0,8,2)
colnames(CuantilesA) <- c('LimInf','LimSup')
colnames(CuantilesD) <- c('LimInf','LimSup')
rownames(CuantilesA) <- c('65','70','75','80','85','90','95','99')
rownames(CuantilesD) <- c('65','70','75','80','85','90','95','99')
CuantilesA[1,1] <-CuantilesData[8]; CuantilesA[1,2] <-CuantilesData[9]
CuantilesA[2,1] <-CuantilesData[7]; CuantilesA[2,2] <-CuantilesData[10]
CuantilesA[3,1] <-CuantilesData[6]; CuantilesA[3,2] <-CuantilesData[11]
CuantilesA[4,1] <-CuantilesData[5]; CuantilesA[4,2] <-CuantilesData[12]
CuantilesA[5,1] <-CuantilesData[4]; CuantilesA[5,2] <-CuantilesData[13]
CuantilesA[6,1] <-CuantilesData[3]; CuantilesA[6,2] <-CuantilesData[14]
CuantilesA[7,1] <-CuantilesData[2]; CuantilesA[7,2] <-CuantilesData[15]
CuantilesA[8,1] <-CuantilesData[1]; CuantilesA[8,2] <-CuantilesData[16]
CuantilesD[1,1] <-Cuantilillos[8];  CuantilesD[1,2] <-Cuantilillos[9]
CuantilesD[2,1] <-Cuantilillos[7];  CuantilesD[2,2] <-Cuantilillos[10]
CuantilesD[3,1] <-Cuantilillos[6];  CuantilesD[3,2] <-Cuantilillos[11]
CuantilesD[4,1] <-Cuantilillos[5];  CuantilesD[4,2] <-Cuantilillos[12]
CuantilesD[5,1] <-Cuantilillos[4];  CuantilesD[5,2] <-Cuantilillos[13]
CuantilesD[6,1] <-Cuantilillos[3];  CuantilesD[6,2] <-Cuantilillos[14]
CuantilesD[7,1] <-Cuantilillos[2];  CuantilesD[7,2] <-Cuantilillos[15]
CuantilesD[8,1] <-Cuantilillos[1];  CuantilesD[8,2] <-Cuantilillos[16]

print(CuantilesD)
##        LimInf    LimSup
## 65 -0.9345893 0.9345893
## 70 -1.0364334 1.0364334
## 75 -1.1503494 1.1503494
## 80 -1.2815516 1.2815516
## 85 -1.4395315 1.4395315
## 90 -1.6448536 1.6448536
## 95 -1.9599640 1.9599640
## 99 -2.5758293 2.5758293
print(CuantilesA)
##        LimInf    LimSup
## 65 -0.8926336 0.8466541
## 70 -0.9421687 0.9875692
## 75 -0.9976178 1.1428700
## 80 -1.0605870 1.3752461
## 85 -1.1334411 1.6895575
## 90 -1.2198720 2.1202686
## 95 -1.4640882 2.5136403
## 99 -2.0100061 3.0865078
col_sequence <- rainbow(n = 7, alpha = 0.35, start = 0, end = 1)
par(mfrow=c(2,1))
hist(tst, breaks = nbreaks, col = col_sequence,
     main = 'Normalized Log2 pEhEx - DATA (sample 2)', lty = 9)

abline(v=CuantilesA[1,1], lty=2, col="darkgoldenrod4"); # 65% INFERIOR
abline(v=CuantilesA[1,2], lty=2, col="darkgoldenrod4"); # 65% SUPERIOR
abline(v=CuantilesA[2,1], lty=2, col="darkblue"); # 70% INFERIOR
abline(v=CuantilesA[2,2], lty=2, col="darkblue") # 70% SUPERIOR
abline(v=CuantilesA[3,1], lty=2, col="aquamarine4"); # 75% INFERIOR
abline(v=CuantilesA[3,2], lty=2, col="aquamarine4"); # 75% SUPERIOR
abline(v=CuantilesA[4,1], lty=2, col="green");  # 80% INFERIOR
abline(v=CuantilesA[4,2], lty=2, col="green"); # 80% SUPERIOR
abline(v=CuantilesA[5,1], lty=2, col="brown"); # 85% INFERIOR
abline(v=CuantilesA[5,2], lty=2, col="brown"); # 85% SUPERIOR
abline(v=CuantilesA[6,1], lty=2, col="red");  # 90% INFERIOR
abline(v=CuantilesA[6,2], lty=2, col="red"); # 90% SUPERIOR
abline(v=CuantilesA[7,1], lty=2, col="blue");  # 95% INFERIOR
abline(v=CuantilesA[7,2], lty=2, col="blue"); # 95% SUPERIOR
abline(v=CuantilesA[8,1], lty=2, col="orange");  # 99% INFERIOR
abline(v=CuantilesA[8,2], lty=2, col="orange"); # 99% SUPERIOR
legend("topright",
       legend=c("65%","70%","75%","80%","85%","90%","95%","99%"), 
       pch=c(1,2,3,4,5,6,7,8),
       col=c("darkgoldenrod4","darkblue","aquamarine4",
             "green", "brown","red","blue","orange"))
hist(tst, breaks = nbreaks, col = col_sequence,
     main = 'Normalized Log2   pEhEx - ADJUSTED (sample 2)', lty=9)

abline(v=CuantilesD[1,1], lty=2, col="darkgoldenrod4"); # 65% INFERIOR
abline(v=CuantilesD[1,2], lty=2, col="darkgoldenrod4"); # 65% SUPERIOR
abline(v=CuantilesD[2,1], lty=2, col="darkblue");  # 70% INFERIOR
abline(v=CuantilesD[2,2], lty=2, col="darkblue"); # 70% SUPERIOR
abline(v=CuantilesD[3,1], lty=2, col="aquamarine4");  # 75% INFERIOR
abline(v=CuantilesD[3,2], lty=2, col="aquamarine4"); # 75% SUPERIOR
abline(v=CuantilesD[4,1], lty=2, col="green");  # 80% INFERIOR
abline(v=CuantilesD[4,2], lty=2, col="green"); # 80% SUPERIOR
abline(v=CuantilesD[5,1], lty=2, col="brown");  # 85% INFERIOR
abline(v=CuantilesD[5,2], lty=2, col="brown"); # 85% SUPERIOR
abline(v=CuantilesD[6,1], lty=2, col="red");  # 90% INFERIOR
abline(v=CuantilesD[6,2], lty=2, col="red"); # 90% SUPERIOR
abline(v=CuantilesD[7,1], lty=2, col="blue");  # 95% INFERIOR
abline(v=CuantilesD[7,2], lty=2, col="blue"); # 95% SUPERIOR
abline(v=CuantilesD[8,1], lty=2, col="orange");  # 99% INFERIOR
abline(v=CuantilesD[8,2], lty=2, col="orange"); # 99% SUPERIOR
legend("topright",
       legend=c("65%","70%","75%","80%","85%","90%","95%","99%"), 
       pch=c(1,2,3,4,5,6,7,8),
       col=c("darkgoldenrod4","darkblue","aquamarine4",
             "green", "brown","red","blue","orange"))

Grafica Cuantiles del \(65\%\) y \(80\%\)

par(mfrow=c(2,1))
hist(tst, breaks = nbreaks, col = col_sequence,
     main = 'Normalized Log2  pEhEx - DATA (sample 2)', lty=9)

abline(v=CuantilesA[1,1], lty=2, col="darkgoldenrod4"); # 65% INFERIOR
abline(v=CuantilesA[1,2], lty=2, col="darkgoldenrod4"); # 65% SUPERIOR
abline(v=CuantilesA[4,1], lty=2, col="green");  # 80% INFERIOR
abline(v=CuantilesA[4,2], lty=2, col="green"); # 80% SUPERIOR
legend("topright",legend=c("65%","80%"), 
       pch=c(1,2),col=c("darkgoldenrod4","green"))
hist(tst, breaks = nbreaks, col = col_sequence,
     main = 'Normalized Log2  BaseMean - ADJUSTED (sample 2)', lty=9)

abline(v=CuantilesD[1,1], lty=2, col="darkgoldenrod4"); # 65% INFERIOR
abline(v=CuantilesD[1,2], lty=2, col="darkgoldenrod4"); # 65% SUPERIOR
abline(v=CuantilesD[4,1], lty=2, col="green");  # 80% INFERIOR
abline(v=CuantilesD[4,2], lty=2, col="green"); # 80% SUPERIOR
legend("topright",legend=c("65%","80%"), 
       pch=c(1,2),col=c("darkgoldenrod4","green"))

Grafica Cuantiles del \(70\%\) y \(85\%\)

par(mfrow=c(2,1))
hist(tst, breaks = nbreaks, col = col_sequence, 
     main = 'Normalized Log2 pEhEx - DATA (sample 2)', lty=9)

abline(v=CuantilesA[2,1], lty=2, col="darkblue"); 
abline(v=CuantilesA[2,2], lty=2, col="darkblue")
abline(v=CuantilesA[5,1], lty=2, col="brown"); 
abline(v=CuantilesA[5,2], lty=2, col="brown")
legend("topright",legend=c("70%","85%"),
       pch=c(1,2),#3,4,5,6,7,8),
       col=c("brown"))
hist(tst, breaks = nbreaks, col = col_sequence,
     main = 'Normalized Log2  pEhEx - ADJUSTED (sample 2)', lty=9)

abline(v=CuantilesD[2,1], lty=2, col="darkblue"); 
abline(v=CuantilesD[2,2], lty=2, col="darkblue")
abline(v=CuantilesD[5,1], lty=2, col="brown"); 
abline(v=CuantilesD[5,2], lty=2, col="brown")
legend("topright",legend=c("70%","85%"),
       pch=c(1,2),#3,4,5,6,7,8),
       col=c("brown"))

Muestra 3

log2sample3 <- data1$log2sample3; head(mean(log2sample3)); head(sd(log2sample3))
## [1] 6.186357
## [1] 3.171257
head(log2sample3,5)
## [1]  8.869952  5.279992 11.017126  9.330508  5.645875
ndata1    <- length(log2sample3)
hist(log2sample3, breaks = nbreaks, col= rainbow(25,0.3), 
     main = 'Log2 sample2')

meanlog2sample3 <- mean(log2sample3); head(meanlog2sample3)
## [1] 6.186357
StdDevlog2sample3 <- sd(log2sample3); head(StdDevlog2sample3)
## [1] 3.171257
Normlog2sample3 <- (log2sample3-meanlog2sample3)/StdDevlog2sample3; head(Normlog2sample3)
## [1]  0.84622446 -0.28580629  1.52329778  0.99145245 -0.17043143 -0.07847701
tst<- Normlog2sample3
hist(tst, breaks = nbreaks, col= 1:5, 
     main = 'Normalized Log2sample1',
     xlab='pEhEx1',
     ylab= 'Frequency pEhEx')

Ajustando Modelos

fw1<-fitdist(tst, "norm")
plotdist(tst, histo = TRUE, demp = TRUE)

nnorm.f <- fitdist(tst,"norm")
summary(nnorm.f)
## Fitting of the distribution ' norm ' by maximum likelihood 
## Parameters : 
##          estimate Std. Error
## mean 2.945427e-17 0.01447452
## sd   9.998952e-01 0.01023499
## Loglikelihood:  -6770.675   AIC:  13545.35   BIC:  13558.29 
## Correlation matrix:
##              mean           sd
## mean 1.000000e+00 1.684231e-11
## sd   1.684231e-11 1.000000e+00
par(mfrow=c(2,2))
denscomp(nnorm.f,legendtext = 'Dist Normal')
qqcomp(nnorm.f,legendtext = 'Dist Normal')
cdfcomp(nnorm.f,legendtext = 'Dist Normal')
ppcomp(nnorm.f,legendtext = 'Dist Normal')

probs <- c();
probs[8] = 0.175;  probs[9] = 0.825; 
probs[7] = 0.15;   probs[10] = 0.85;   
probs[6] = 0.125;  probs[11] = 0.875; 
probs[5] = 0.1;    probs[12] = 0.9;    
probs[4] = 0.075;  probs[13] = 0.925; 
probs[3] = 0.05;   probs[14] = 0.95;   
probs[2] = 0.025;  probs[15] = 0.975; 
probs[1] = 0.005;  probs[16] = 0.995;  
CuantilesData <- quantile(tst,prob = probs)
CuantilesModel <- qnorm(probs, mean=0, sd=1)
Cuantilillos <- t(CuantilesModel)
colnames(Cuantilillos) <- c('0.5%','2.5%','5%','7.5%',
                            '10%','12.5%','15%','17.5%',
                            '82.5%','85%','87.5%','90%',
                            '92.5%','95%','97.5%','99.5%')
Cuantilillos <- t(Cuantilillos)
colnames(Cuantilillos) <- c('Cuantiles Ajuste')
print(Cuantilillos)
##       Cuantiles Ajuste
## 0.5%        -2.5758293
## 2.5%        -1.9599640
## 5%          -1.6448536
## 7.5%        -1.4395315
## 10%         -1.2815516
## 12.5%       -1.1503494
## 15%         -1.0364334
## 17.5%       -0.9345893
## 82.5%        0.9345893
## 85%          1.0364334
## 87.5%        1.1503494
## 90%          1.2815516
## 92.5%        1.4395315
## 95%          1.6448536
## 97.5%        1.9599640
## 99.5%        2.5758293
CuantilesA <- matrix(0,8,2)
CuantilesD <- matrix(0,8,2)
colnames(CuantilesA) <- c('LimInf','LimSup')
colnames(CuantilesD) <- c('LimInf','LimSup')
rownames(CuantilesA) <- c('65','70','75','80','85','90','95','99')
rownames(CuantilesD) <- c('65','70','75','80','85','90','95','99')
CuantilesA[1,1] <-CuantilesData[8]; CuantilesA[1,2] <-CuantilesData[9]
CuantilesA[2,1] <-CuantilesData[7]; CuantilesA[2,2] <-CuantilesData[10]
CuantilesA[3,1] <-CuantilesData[6]; CuantilesA[3,2] <-CuantilesData[11]
CuantilesA[4,1] <-CuantilesData[5]; CuantilesA[4,2] <-CuantilesData[12]
CuantilesA[5,1] <-CuantilesData[4]; CuantilesA[5,2] <-CuantilesData[13]
CuantilesA[6,1] <-CuantilesData[3]; CuantilesA[6,2] <-CuantilesData[14]
CuantilesA[7,1] <-CuantilesData[2]; CuantilesA[7,2] <-CuantilesData[15]
CuantilesA[8,1] <-CuantilesData[1]; CuantilesA[8,2] <-CuantilesData[16]
CuantilesD[1,1] <-Cuantilillos[8];  CuantilesD[1,2] <-Cuantilillos[9]
CuantilesD[2,1] <-Cuantilillos[7];  CuantilesD[2,2] <-Cuantilillos[10]
CuantilesD[3,1] <-Cuantilillos[6];  CuantilesD[3,2] <-Cuantilillos[11]
CuantilesD[4,1] <-Cuantilillos[5];  CuantilesD[4,2] <-Cuantilillos[12]
CuantilesD[5,1] <-Cuantilillos[4];  CuantilesD[5,2] <-Cuantilillos[13]
CuantilesD[6,1] <-Cuantilillos[3];  CuantilesD[6,2] <-Cuantilillos[14]
CuantilesD[7,1] <-Cuantilillos[2];  CuantilesD[7,2] <-Cuantilillos[15]
CuantilesD[8,1] <-Cuantilillos[1];  CuantilesD[8,2] <-Cuantilillos[16]
print(CuantilesD)
##        LimInf    LimSup
## 65 -0.9345893 0.9345893
## 70 -1.0364334 1.0364334
## 75 -1.1503494 1.1503494
## 80 -1.2815516 1.2815516
## 85 -1.4395315 1.4395315
## 90 -1.6448536 1.6448536
## 95 -1.9599640 1.9599640
## 99 -2.5758293 2.5758293
print(CuantilesA)
##        LimInf    LimSup
## 65 -0.8676459 0.8379706
## 70 -0.9660265 0.9701830
## 75 -1.0458574 1.1161493
## 80 -1.1427428 1.3265284
## 85 -1.2660057 1.6213606
## 90 -1.4356115 2.0178765
## 95 -1.7090932 2.4795401
## 99 -1.9507587 3.0829063

CreaciĂ³n de histogramas

col_sequence <- rainbow(n = 7, alpha = 0.35, start = 0, end = 1)
par(mfrow=c(2,1))
hist(tst, breaks = nbreaks, col = col_sequence,
     main = 'Normalized Log2 pEhEx - DATA (sample 3)', lty = 9)

abline(v=CuantilesA[1,1], lty=2, col="darkgoldenrod4"); # 65% INFERIOR
abline(v=CuantilesA[1,2], lty=2, col="darkgoldenrod4"); # 65% SUPERIOR
abline(v=CuantilesA[2,1], lty=2, col="darkblue"); # 70% INFERIOR
abline(v=CuantilesA[2,2], lty=2, col="darkblue") # 70% SUPERIOR
abline(v=CuantilesA[3,1], lty=2, col="aquamarine4"); # 75% INFERIOR
abline(v=CuantilesA[3,2], lty=2, col="aquamarine4"); # 75% SUPERIOR
abline(v=CuantilesA[4,1], lty=2, col="green");  # 80% INFERIOR
abline(v=CuantilesA[4,2], lty=2, col="green"); # 80% SUPERIOR
abline(v=CuantilesA[5,1], lty=2, col="brown"); # 85% INFERIOR
abline(v=CuantilesA[5,2], lty=2, col="brown"); # 85% SUPERIOR
abline(v=CuantilesA[6,1], lty=2, col="red");  # 90% INFERIOR
abline(v=CuantilesA[6,2], lty=2, col="red"); # 90% SUPERIOR
abline(v=CuantilesA[7,1], lty=2, col="blue");  # 95% INFERIOR
abline(v=CuantilesA[7,2], lty=2, col="blue"); # 95% SUPERIOR
abline(v=CuantilesA[8,1], lty=2, col="orange");  # 99% INFERIOR
abline(v=CuantilesA[8,2], lty=2, col="orange"); # 99% SUPERIOR
legend("topright",
       legend=c("65%","70%","75%","80%","85%","90%","95%","99%"), 
       pch=c(1,2,3,4,5,6,7,8),
       col=c("darkgoldenrod4","darkblue","aquamarine4",
             "green", "brown","red","blue","orange"))
hist(tst, breaks = nbreaks, col = col_sequence,
     main = 'Normalized Log2   pEhEx - ADJUSTED (sample 3)', lty=9)

abline(v=CuantilesD[1,1], lty=2, col="darkgoldenrod4"); # 65% INFERIOR
abline(v=CuantilesD[1,2], lty=2, col="darkgoldenrod4"); # 65% SUPERIOR
abline(v=CuantilesD[2,1], lty=2, col="darkblue");  # 70% INFERIOR
abline(v=CuantilesD[2,2], lty=2, col="darkblue"); # 70% SUPERIOR
abline(v=CuantilesD[3,1], lty=2, col="aquamarine4");  # 75% INFERIOR
abline(v=CuantilesD[3,2], lty=2, col="aquamarine4"); # 75% SUPERIOR
abline(v=CuantilesD[4,1], lty=2, col="green");  # 80% INFERIOR
abline(v=CuantilesD[4,2], lty=2, col="green"); # 80% SUPERIOR
abline(v=CuantilesD[5,1], lty=2, col="brown");  # 85% INFERIOR
abline(v=CuantilesD[5,2], lty=2, col="brown"); # 85% SUPERIOR
abline(v=CuantilesD[6,1], lty=2, col="red");  # 90% INFERIOR
abline(v=CuantilesD[6,2], lty=2, col="red"); # 90% SUPERIOR
abline(v=CuantilesD[7,1], lty=2, col="blue");  # 95% INFERIOR
abline(v=CuantilesD[7,2], lty=2, col="blue"); # 95% SUPERIOR
abline(v=CuantilesD[8,1], lty=2, col="orange");  # 99% INFERIOR
abline(v=CuantilesD[8,2], lty=2, col="orange"); # 99% SUPERIOR
legend("topright",
       legend=c("65%","70%","75%","80%","85%","90%","95%","99%"), 
       pch=c(1,2,3,4,5,6,7,8),
       col=c("darkgoldenrod4","darkblue","aquamarine4",
             "green", "brown","red","blue","orange"))

Grafica Cuantiles del \(65\%\) y \(80\%\)

par(mfrow=c(2,1))
hist(tst, breaks = nbreaks, col = col_sequence,
     main = 'Normalized Log2  pEhEx - DATA (sample 2)', lty=9)

abline(v=CuantilesA[1,1], lty=2, col="darkgoldenrod4"); # 65% INFERIOR
abline(v=CuantilesA[1,2], lty=2, col="darkgoldenrod4"); # 65% SUPERIOR
abline(v=CuantilesA[4,1], lty=2, col="green");  # 80% INFERIOR
abline(v=CuantilesA[4,2], lty=2, col="green"); # 80% SUPERIOR
legend("topright",legend=c("65%","80%"), 
       pch=c(1,2),col=c("darkgoldenrod4","green"))
hist(tst, breaks = nbreaks, col = col_sequence,
     main = 'Normalized Log2  BaseMean - ADJUSTED (sample 3)', lty=9)

abline(v=CuantilesD[1,1], lty=2, col="darkgoldenrod4"); # 65% INFERIOR
abline(v=CuantilesD[1,2], lty=2, col="darkgoldenrod4"); # 65% SUPERIOR
abline(v=CuantilesD[4,1], lty=2, col="green");  # 80% INFERIOR
abline(v=CuantilesD[4,2], lty=2, col="green"); # 80% SUPERIOR
legend("topright",legend=c("65%","80%"), 
       pch=c(1,2),col=c("darkgoldenrod4","green"))

Grafica Cuantiles del \(70\%\) y \(85\%\)

par(mfrow=c(2,1))
hist(tst, breaks = nbreaks, col = col_sequence, 
     main = 'Normalized Log2 pEhEx - DATA (sample 3)', lty=9)

abline(v=CuantilesA[2,1], lty=2, col="darkblue"); 
abline(v=CuantilesA[2,2], lty=2, col="darkblue")
abline(v=CuantilesA[5,1], lty=2, col="brown"); 
abline(v=CuantilesA[5,2], lty=2, col="brown")
legend("topright",legend=c("70%","85%"),
       pch=c(1,2),#3,4,5,6,7,8),
       col=c("brown"))
hist(tst, breaks = nbreaks, col = col_sequence,
     main = 'Normalized Log2  pEhEx - ADJUSTED (sample 3)', lty=9)

abline(v=CuantilesD[2,1], lty=2, col="darkblue"); 
abline(v=CuantilesD[2,2], lty=2, col="darkblue")
abline(v=CuantilesD[5,1], lty=2, col="brown"); 
abline(v=CuantilesD[5,2], lty=2, col="brown")
legend("topright",legend=c("70%","85%"),
       pch=c(1,2),#3,4,5,6,7,8),
       col=c("brown"))

Muestra pEhExvsCDC51

log2vsCDC51 <- data1$log2samplevsCDC51; head(mean(log2vsCDC51)); head(sd(log2vsCDC51))
## [1] 6.244372
## [1] 2.880412
head(log2vsCDC51,5)
## [1] 6.201533 6.807708 9.777801 8.946924 3.787731
ndata1    <- length(log2vsCDC51)
hist(log2vsCDC51, breaks = nbreaks, col= rainbow(25,0.3), 
     main = 'Log2vsCDC51')

meanlog2vsCDC51 <- mean(log2vsCDC51); head(meanlog2vsCDC51)
## [1] 6.244372
StdDevlog2vsCDC51 <- sd(log2vsCDC51); head(StdDevlog2vsCDC51)
## [1] 2.880412
Normlog2vsCDC51 <- (log2vsCDC51-meanlog2vsCDC51)/StdDevlog2vsCDC51; head(Normlog2vsCDC51)
## [1] -0.01487273  0.19557464  1.22670936  0.93825188 -0.85287855 -0.12253093
tst<- Normlog2vsCDC51

Primer histograma

hist(tst, breaks = nbreaks, col= 1:5, 
     main = 'Normalized Log2vsCDC51',
     xlab='pEhEx1',
     ylab= 'Frequency pEhEx')

Ajustando modelo

fw1<-fitdist(tst, "norm")
plotdist(tst, histo = TRUE, demp = TRUE)

nnorm.f <- fitdist(tst,"norm")
summary(nnorm.f)
## Fitting of the distribution ' norm ' by maximum likelihood 
## Parameters : 
##          estimate Std. Error
## mean 6.276949e-17 0.01447452
## sd   9.998952e-01 0.01023499
## Loglikelihood:  -6770.675   AIC:  13545.35   BIC:  13558.29 
## Correlation matrix:
##      mean sd
## mean    1  0
## sd      0  1
par(mfrow=c(2,2))
denscomp(nnorm.f,legendtext = 'Dist Normal')
qqcomp(nnorm.f,legendtext = 'Dist Normal')
cdfcomp(nnorm.f,legendtext = 'Dist Normal')
ppcomp(nnorm.f,legendtext = 'Dist Normal')

probs <- c();
probs[8] = 0.175;  probs[9] = 0.825; 
probs[7] = 0.15;   probs[10] = 0.85;   
probs[6] = 0.125;  probs[11] = 0.875; 
probs[5] = 0.1;    probs[12] = 0.9;    
probs[4] = 0.075;  probs[13] = 0.925; 
probs[3] = 0.05;   probs[14] = 0.95;   
probs[2] = 0.025;  probs[15] = 0.975; 
probs[1] = 0.005;  probs[16] = 0.995;  
CuantilesData <- quantile(tst,prob = probs)
CuantilesModel <- qnorm(probs, mean=0, sd=1)
Cuantilillos <- t(CuantilesModel)
colnames(Cuantilillos) <- c('0.5%','2.5%','5%','7.5%',
                            '10%','12.5%','15%','17.5%',
                            '82.5%','85%','87.5%','90%',
                            '92.5%','95%','97.5%','99.5%')
Cuantilillos <- t(Cuantilillos)
colnames(Cuantilillos) <- c('Cuantiles Ajuste')
print(Cuantilillos)
##       Cuantiles Ajuste
## 0.5%        -2.5758293
## 2.5%        -1.9599640
## 5%          -1.6448536
## 7.5%        -1.4395315
## 10%         -1.2815516
## 12.5%       -1.1503494
## 15%         -1.0364334
## 17.5%       -0.9345893
## 82.5%        0.9345893
## 85%          1.0364334
## 87.5%        1.1503494
## 90%          1.2815516
## 92.5%        1.4395315
## 95%          1.6448536
## 97.5%        1.9599640
## 99.5%        2.5758293
CuantilesA <- matrix(0,8,2)
CuantilesD <- matrix(0,8,2)
colnames(CuantilesA) <- c('LimInf','LimSup')
colnames(CuantilesD) <- c('LimInf','LimSup')
rownames(CuantilesA) <- c('65','70','75','80','85','90','95','99')
rownames(CuantilesD) <- c('65','70','75','80','85','90','95','99')
CuantilesA[1,1] <-CuantilesData[8]; CuantilesA[1,2] <-CuantilesData[9]
CuantilesA[2,1] <-CuantilesData[7]; CuantilesA[2,2] <-CuantilesData[10]
CuantilesA[3,1] <-CuantilesData[6]; CuantilesA[3,2] <-CuantilesData[11]
CuantilesA[4,1] <-CuantilesData[5]; CuantilesA[4,2] <-CuantilesData[12]
CuantilesA[5,1] <-CuantilesData[4]; CuantilesA[5,2] <-CuantilesData[13]
CuantilesA[6,1] <-CuantilesData[3]; CuantilesA[6,2] <-CuantilesData[14]
CuantilesA[7,1] <-CuantilesData[2]; CuantilesA[7,2] <-CuantilesData[15]
CuantilesA[8,1] <-CuantilesData[1]; CuantilesA[8,2] <-CuantilesData[16]
CuantilesD[1,1] <-Cuantilillos[8];  CuantilesD[1,2] <-Cuantilillos[9]
CuantilesD[2,1] <-Cuantilillos[7];  CuantilesD[2,2] <-Cuantilillos[10]
CuantilesD[3,1] <-Cuantilillos[6];  CuantilesD[3,2] <-Cuantilillos[11]
CuantilesD[4,1] <-Cuantilillos[5];  CuantilesD[4,2] <-Cuantilillos[12]
CuantilesD[5,1] <-Cuantilillos[4];  CuantilesD[5,2] <-Cuantilillos[13]
CuantilesD[6,1] <-Cuantilillos[3];  CuantilesD[6,2] <-Cuantilillos[14]
CuantilesD[7,1] <-Cuantilillos[2];  CuantilesD[7,2] <-Cuantilillos[15]
CuantilesD[8,1] <-Cuantilillos[1];  CuantilesD[8,2] <-Cuantilillos[16]
print(CuantilesD)
##        LimInf    LimSup
## 65 -0.9345893 0.9345893
## 70 -1.0364334 1.0364334
## 75 -1.1503494 1.1503494
## 80 -1.2815516 1.2815516
## 85 -1.4395315 1.4395315
## 90 -1.6448536 1.6448536
## 95 -1.9599640 1.9599640
## 99 -2.5758293 2.5758293
print(CuantilesA)
##        LimInf    LimSup
## 65 -0.8528786 0.8216616
## 70 -0.9073590 0.9496778
## 75 -0.9073590 1.1007491
## 80 -0.9684970 1.3308952
## 85 -1.0381490 1.6867728
## 90 -1.1190762 2.1306178
## 95 -1.2156475 2.6928135
## 99 -2.1678747 3.3316192

Histogramas

col_sequence <- rainbow(n = 7, alpha = 0.35, start = 0, end = 1)
par(mfrow=c(2,1))
hist(tst, breaks = nbreaks, col = col_sequence,
     main = 'Normalized Log2vsCDC51 pEhEx - DATA', lty = 9)

abline(v=CuantilesA[1,1], lty=2, col="darkgoldenrod4"); # 65% INFERIOR
abline(v=CuantilesA[1,2], lty=2, col="darkgoldenrod4"); # 65% SUPERIOR
abline(v=CuantilesA[2,1], lty=2, col="darkblue"); # 70% INFERIOR
abline(v=CuantilesA[2,2], lty=2, col="darkblue") # 70% SUPERIOR
abline(v=CuantilesA[3,1], lty=2, col="aquamarine4"); # 75% INFERIOR
abline(v=CuantilesA[3,2], lty=2, col="aquamarine4"); # 75% SUPERIOR
abline(v=CuantilesA[4,1], lty=2, col="green");  # 80% INFERIOR
abline(v=CuantilesA[4,2], lty=2, col="green"); # 80% SUPERIOR
abline(v=CuantilesA[5,1], lty=2, col="brown"); # 85% INFERIOR
abline(v=CuantilesA[5,2], lty=2, col="brown"); # 85% SUPERIOR
abline(v=CuantilesA[6,1], lty=2, col="red");  # 90% INFERIOR
abline(v=CuantilesA[6,2], lty=2, col="red"); # 90% SUPERIOR
abline(v=CuantilesA[7,1], lty=2, col="blue");  # 95% INFERIOR
abline(v=CuantilesA[7,2], lty=2, col="blue"); # 95% SUPERIOR
abline(v=CuantilesA[8,1], lty=2, col="orange");  # 99% INFERIOR
abline(v=CuantilesA[8,2], lty=2, col="orange"); # 99% SUPERIOR
legend("topright",
       legend=c("65%","70%","75%","80%","85%","90%","95%","99%"), 
       pch=c(1,2,3,4,5,6,7,8),
       col=c("darkgoldenrod4","darkblue","aquamarine4",
             "green", "brown","red","blue","orange"))
hist(tst, breaks = nbreaks, col = col_sequence,
     main = 'Normalized Log2vsCDC51   pEhEx - ADJUSTED', lty=9)

abline(v=CuantilesD[1,1], lty=2, col="darkgoldenrod4"); # 65% INFERIOR
abline(v=CuantilesD[1,2], lty=2, col="darkgoldenrod4"); # 65% SUPERIOR
abline(v=CuantilesD[2,1], lty=2, col="darkblue");  # 70% INFERIOR
abline(v=CuantilesD[2,2], lty=2, col="darkblue"); # 70% SUPERIOR
abline(v=CuantilesD[3,1], lty=2, col="aquamarine4");  # 75% INFERIOR
abline(v=CuantilesD[3,2], lty=2, col="aquamarine4"); # 75% SUPERIOR
abline(v=CuantilesD[4,1], lty=2, col="green");  # 80% INFERIOR
abline(v=CuantilesD[4,2], lty=2, col="green"); # 80% SUPERIOR
abline(v=CuantilesD[5,1], lty=2, col="brown");  # 85% INFERIOR
abline(v=CuantilesD[5,2], lty=2, col="brown"); # 85% SUPERIOR
abline(v=CuantilesD[6,1], lty=2, col="red");  # 90% INFERIOR
abline(v=CuantilesD[6,2], lty=2, col="red"); # 90% SUPERIOR
abline(v=CuantilesD[7,1], lty=2, col="blue");  # 95% INFERIOR
abline(v=CuantilesD[7,2], lty=2, col="blue"); # 95% SUPERIOR
abline(v=CuantilesD[8,1], lty=2, col="orange");  # 99% INFERIOR
abline(v=CuantilesD[8,2], lty=2, col="orange"); # 99% SUPERIOR
legend("topright",
       legend=c("65%","70%","75%","80%","85%","90%","95%","99%"), 
       pch=c(1,2,3,4,5,6,7,8),
       col=c("darkgoldenrod4","darkblue","aquamarine4",
             "green", "brown","red","blue","orange"))

Grafica Cuantiles del \(65\%\) y \(80\%\)

par(mfrow=c(2,1))
hist(tst, breaks = nbreaks, col = col_sequence,
     main = 'Normalized Log2vsCDC51  pEhEx - DATA', lty=9)

abline(v=CuantilesA[1,1], lty=2, col="darkgoldenrod4"); # 65% INFERIOR
abline(v=CuantilesA[1,2], lty=2, col="darkgoldenrod4"); # 65% SUPERIOR
abline(v=CuantilesA[4,1], lty=2, col="green");  # 80% INFERIOR
abline(v=CuantilesA[4,2], lty=2, col="green"); # 80% SUPERIOR
legend("topright",legend=c("65%","80%"), 
       pch=c(1,2),col=c("darkgoldenrod4","green"))
hist(tst, breaks = nbreaks, col = col_sequence,
     main = 'Normalized Log2vsCDC51  - ADJUSTED', lty=9)

abline(v=CuantilesD[1,1], lty=2, col="darkgoldenrod4"); # 65% INFERIOR
abline(v=CuantilesD[1,2], lty=2, col="darkgoldenrod4"); # 65% SUPERIOR
abline(v=CuantilesD[4,1], lty=2, col="green");  # 80% INFERIOR
abline(v=CuantilesD[4,2], lty=2, col="green"); # 80% SUPERIOR
legend("topright",legend=c("65%","80%"), 
       pch=c(1,2),col=c("darkgoldenrod4","green"))

Grafica Cuantiles del \(70\%\) y \(85\%\)

par(mfrow=c(2,1))
hist(tst, breaks = nbreaks, col = col_sequence, 
     main = 'Normalized Log2vsCDC51 pEhEx - DATA', lty=9)

abline(v=CuantilesA[2,1], lty=2, col="darkblue"); 
abline(v=CuantilesA[2,2], lty=2, col="darkblue")
abline(v=CuantilesA[5,1], lty=2, col="brown"); 
abline(v=CuantilesA[5,2], lty=2, col="brown")
legend("topright",legend=c("70%","85%"),
       pch=c(1,2),#3,4,5,6,7,8),
       col=c("brown"))
hist(tst, breaks = nbreaks, col = col_sequence,
     main = 'Normalized Log2vsCDC51  pEhEx - ADJUSTED', lty=9)

abline(v=CuantilesD[2,1], lty=2, col="darkblue"); 
abline(v=CuantilesD[2,2], lty=2, col="darkblue")
abline(v=CuantilesD[5,1], lty=2, col="brown"); 
abline(v=CuantilesD[5,2], lty=2, col="brown")
legend("topright",legend=c("70%","85%"),
       pch=c(1,2),#3,4,5,6,7,8),
       col=c("brown"))

Muestra pEhExvsCDC52

log2vsCDC52 <- data1$log2samplevsCDC52; head(mean(log2vsCDC52)); head(sd(log2vsCDC52))
## [1] 6.269726
## [1] 2.952289
head(log2vsCDC52,5)
## [1] 5.392236 7.192281 9.556532 8.999192 6.765073

Primer Histograma

ndata1    <- length(log2vsCDC52)
hist(log2vsCDC52, breaks = nbreaks, col= rainbow(25,0.3), 
     main = 'Log2vsCDC52')

meanlog2vsCDC52 <- mean(log2vsCDC52); head(meanlog2vsCDC52)
## [1] 6.269726
StdDevlog2vsCDC52 <- sd(log2vsCDC52); head(StdDevlog2vsCDC52)
## [1] 2.952289
Normlog2vsCDC52 <- (log2vsCDC52-meanlog2vsCDC52)/StdDevlog2vsCDC52; head(Normlog2vsCDC52)
## [1] -0.2972235  0.3124880  1.1133080  0.9245256  0.1677843 -0.2837806
tst<- Normlog2vsCDC52

** Segundo Histograma**

hist(tst, breaks = nbreaks, col= 1:5, 
     main = 'Normalized Log2vsCDC52',
     xlab='pEhEx1',
     ylab= 'Frequency pEhEx')

Ajustando modelo

fw1<-fitdist(tst, "norm")
plotdist(tst, histo = TRUE, demp = TRUE)

nnorm.f <- fitdist(tst,"norm")
summary(nnorm.f)
## Fitting of the distribution ' norm ' by maximum likelihood 
## Parameters : 
##           estimate Std. Error
## mean -3.587454e-18 0.01447452
## sd    9.998952e-01 0.01023499
## Loglikelihood:  -6770.675   AIC:  13545.35   BIC:  13558.29 
## Correlation matrix:
##              mean           sd
## mean 1.000000e+00 1.684231e-11
## sd   1.684231e-11 1.000000e+00
par(mfrow=c(2,2))
denscomp(nnorm.f,legendtext = 'Dist Normal')
qqcomp(nnorm.f,legendtext = 'Dist Normal')
cdfcomp(nnorm.f,legendtext = 'Dist Normal')
ppcomp(nnorm.f,legendtext = 'Dist Normal')

CĂ¡lculo de cuantiles

probs <- c();
probs[8] = 0.175;  probs[9] = 0.825; 
probs[7] = 0.15;   probs[10] = 0.85;   
probs[6] = 0.125;  probs[11] = 0.875; 
probs[5] = 0.1;    probs[12] = 0.9;    
probs[4] = 0.075;  probs[13] = 0.925; 
probs[3] = 0.05;   probs[14] = 0.95;   
probs[2] = 0.025;  probs[15] = 0.975; 
probs[1] = 0.005;  probs[16] = 0.995;  
CuantilesData <- quantile(tst,prob = probs)
CuantilesModel <- qnorm(probs, mean=0, sd=1)
Cuantilillos <- t(CuantilesModel)
colnames(Cuantilillos) <- c('0.5%','2.5%','5%','7.5%',
                            '10%','12.5%','15%','17.5%',
                            '82.5%','85%','87.5%','90%',
                            '92.5%','95%','97.5%','99.5%')
Cuantilillos <- t(Cuantilillos)
colnames(Cuantilillos) <- c('Cuantiles Ajuste')
print(Cuantilillos)
##       Cuantiles Ajuste
## 0.5%        -2.5758293
## 2.5%        -1.9599640
## 5%          -1.6448536
## 7.5%        -1.4395315
## 10%         -1.2815516
## 12.5%       -1.1503494
## 15%         -1.0364334
## 17.5%       -0.9345893
## 82.5%        0.9345893
## 85%          1.0364334
## 87.5%        1.1503494
## 90%          1.2815516
## 92.5%        1.4395315
## 95%          1.6448536
## 97.5%        1.9599640
## 99.5%        2.5758293
CuantilesA <- matrix(0,8,2)
CuantilesD <- matrix(0,8,2)
colnames(CuantilesA) <- c('LimInf','LimSup')
colnames(CuantilesD) <- c('LimInf','LimSup')
rownames(CuantilesA) <- c('65','70','75','80','85','90','95','99')
rownames(CuantilesD) <- c('65','70','75','80','85','90','95','99')
CuantilesA[1,1] <-CuantilesData[8]; CuantilesA[1,2] <-CuantilesData[9]
CuantilesA[2,1] <-CuantilesData[7]; CuantilesA[2,2] <-CuantilesData[10]
CuantilesA[3,1] <-CuantilesData[6]; CuantilesA[3,2] <-CuantilesData[11]
CuantilesA[4,1] <-CuantilesData[5]; CuantilesA[4,2] <-CuantilesData[12]
CuantilesA[5,1] <-CuantilesData[4]; CuantilesA[5,2] <-CuantilesData[13]
CuantilesA[6,1] <-CuantilesData[3]; CuantilesA[6,2] <-CuantilesData[14]
CuantilesA[7,1] <-CuantilesData[2]; CuantilesA[7,2] <-CuantilesData[15]
CuantilesA[8,1] <-CuantilesData[1]; CuantilesA[8,2] <-CuantilesData[16]
CuantilesD[1,1] <-Cuantilillos[8];  CuantilesD[1,2] <-Cuantilillos[9]
CuantilesD[2,1] <-Cuantilillos[7];  CuantilesD[2,2] <-Cuantilillos[10]
CuantilesD[3,1] <-Cuantilillos[6];  CuantilesD[3,2] <-Cuantilillos[11]
CuantilesD[4,1] <-Cuantilillos[5];  CuantilesD[4,2] <-Cuantilillos[12]
CuantilesD[5,1] <-Cuantilillos[4];  CuantilesD[5,2] <-Cuantilillos[13]
CuantilesD[6,1] <-Cuantilillos[3];  CuantilesD[6,2] <-Cuantilillos[14]
CuantilesD[7,1] <-Cuantilillos[2];  CuantilesD[7,2] <-Cuantilillos[15]
CuantilesD[8,1] <-Cuantilillos[1];  CuantilesD[8,2] <-Cuantilillos[16]
print(CuantilesD)
##        LimInf    LimSup
## 65 -0.9345893 0.9345893
## 70 -1.0364334 1.0364334
## 75 -1.1503494 1.1503494
## 80 -1.2815516 1.2815516
## 85 -1.4395315 1.4395315
## 90 -1.6448536 1.6448536
## 95 -1.9599640 1.9599640
## 99 -2.5758293 2.5758293
print(CuantilesA)
##        LimInf    LimSup
## 65 -0.8380866 0.7932340
## 70 -0.8811551 0.9359679
## 75 -0.9283894 1.1117853
## 80 -1.0392501 1.3412158
## 85 -1.1058050 1.6629743
## 90 -1.1828753 2.0953140
## 95 -1.3871587 2.6382746
## 99 -2.1236833 3.2437321

Histogramas

col_sequence <- rainbow(n = 7, alpha = 0.35, start = 0, end = 1)
par(mfrow=c(2,1))
hist(tst, breaks = nbreaks, col = col_sequence,
     main = 'Normalized Log2vsCDC52 pEhEx - DATA', lty = 9)

abline(v=CuantilesA[1,1], lty=2, col="darkgoldenrod4"); # 65% INFERIOR
abline(v=CuantilesA[1,2], lty=2, col="darkgoldenrod4"); # 65% SUPERIOR
abline(v=CuantilesA[2,1], lty=2, col="darkblue"); # 70% INFERIOR
abline(v=CuantilesA[2,2], lty=2, col="darkblue") # 70% SUPERIOR
abline(v=CuantilesA[3,1], lty=2, col="aquamarine4"); # 75% INFERIOR
abline(v=CuantilesA[3,2], lty=2, col="aquamarine4"); # 75% SUPERIOR
abline(v=CuantilesA[4,1], lty=2, col="green");  # 80% INFERIOR
abline(v=CuantilesA[4,2], lty=2, col="green"); # 80% SUPERIOR
abline(v=CuantilesA[5,1], lty=2, col="brown"); # 85% INFERIOR
abline(v=CuantilesA[5,2], lty=2, col="brown"); # 85% SUPERIOR
abline(v=CuantilesA[6,1], lty=2, col="red");  # 90% INFERIOR
abline(v=CuantilesA[6,2], lty=2, col="red"); # 90% SUPERIOR
abline(v=CuantilesA[7,1], lty=2, col="blue");  # 95% INFERIOR
abline(v=CuantilesA[7,2], lty=2, col="blue"); # 95% SUPERIOR
abline(v=CuantilesA[8,1], lty=2, col="orange");  # 99% INFERIOR
abline(v=CuantilesA[8,2], lty=2, col="orange"); # 99% SUPERIOR
legend("topright",
       legend=c("65%","70%","75%","80%","85%","90%","95%","99%"), 
       pch=c(1,2,3,4,5,6,7,8),
       col=c("darkgoldenrod4","darkblue","aquamarine4",
             "green", "brown","red","blue","orange"))
hist(tst, breaks = nbreaks, col = col_sequence,
     main = 'Normalized Log2vsCDC52   pEhEx - ADJUSTED', lty=9)

abline(v=CuantilesD[1,1], lty=2, col="darkgoldenrod4"); # 65% INFERIOR
abline(v=CuantilesD[1,2], lty=2, col="darkgoldenrod4"); # 65% SUPERIOR
abline(v=CuantilesD[2,1], lty=2, col="darkblue");  # 70% INFERIOR
abline(v=CuantilesD[2,2], lty=2, col="darkblue"); # 70% SUPERIOR
abline(v=CuantilesD[3,1], lty=2, col="aquamarine4");  # 75% INFERIOR
abline(v=CuantilesD[3,2], lty=2, col="aquamarine4"); # 75% SUPERIOR
abline(v=CuantilesD[4,1], lty=2, col="green");  # 80% INFERIOR
abline(v=CuantilesD[4,2], lty=2, col="green"); # 80% SUPERIOR
abline(v=CuantilesD[5,1], lty=2, col="brown");  # 85% INFERIOR
abline(v=CuantilesD[5,2], lty=2, col="brown"); # 85% SUPERIOR
abline(v=CuantilesD[6,1], lty=2, col="red");  # 90% INFERIOR
abline(v=CuantilesD[6,2], lty=2, col="red"); # 90% SUPERIOR
abline(v=CuantilesD[7,1], lty=2, col="blue");  # 95% INFERIOR
abline(v=CuantilesD[7,2], lty=2, col="blue"); # 95% SUPERIOR
abline(v=CuantilesD[8,1], lty=2, col="orange");  # 99% INFERIOR
abline(v=CuantilesD[8,2], lty=2, col="orange"); # 99% SUPERIOR
legend("topright",
       legend=c("65%","70%","75%","80%","85%","90%","95%","99%"), 
       pch=c(1,2,3,4,5,6,7,8),
       col=c("darkgoldenrod4","darkblue","aquamarine4",
             "green", "brown","red","blue","orange"))

Grafica Cuantiles del \(65\%\) y \(80\%\)

par(mfrow=c(2,1))
hist(tst, breaks = nbreaks, col = col_sequence,
     main = 'Normalized Log2vsCDC52  pEhEx - DATA', lty=9)

abline(v=CuantilesA[1,1], lty=2, col="darkgoldenrod4"); # 65% INFERIOR
abline(v=CuantilesA[1,2], lty=2, col="darkgoldenrod4"); # 65% SUPERIOR
abline(v=CuantilesA[4,1], lty=2, col="green");  # 80% INFERIOR
abline(v=CuantilesA[4,2], lty=2, col="green"); # 80% SUPERIOR
legend("topright",legend=c("65%","80%"), 
       pch=c(1,2),col=c("darkgoldenrod4","green"))
hist(tst, breaks = nbreaks, col = col_sequence,
     main = 'Normalized Log2vsCDC52  - ADJUSTED', lty=9)

abline(v=CuantilesD[1,1], lty=2, col="darkgoldenrod4"); # 65% INFERIOR
abline(v=CuantilesD[1,2], lty=2, col="darkgoldenrod4"); # 65% SUPERIOR
abline(v=CuantilesD[4,1], lty=2, col="green");  # 80% INFERIOR
abline(v=CuantilesD[4,2], lty=2, col="green"); # 80% SUPERIOR
legend("topright",legend=c("65%","80%"), 
       pch=c(1,2),col=c("darkgoldenrod4","green"))

Grafica Cuantiles del \(70\%\) y \(85\%\)

par(mfrow=c(2,1))
hist(tst, breaks = nbreaks, col = col_sequence, 
     main = 'Normalized Log2vsCDC52 pEhEx - DATA', lty=9)

abline(v=CuantilesA[2,1], lty=2, col="darkblue"); 
abline(v=CuantilesA[2,2], lty=2, col="darkblue")
abline(v=CuantilesA[5,1], lty=2, col="brown"); 
abline(v=CuantilesA[5,2], lty=2, col="brown")
legend("topright",legend=c("70%","85%"),
       pch=c(1,2),#3,4,5,6,7,8),
       col=c("brown"))
hist(tst, breaks = nbreaks, col = col_sequence,
     main = 'Normalized Log2vsCDC52  pEhEx - ADJUSTED', lty=9)

abline(v=CuantilesD[2,1], lty=2, col="darkblue"); 
abline(v=CuantilesD[2,2], lty=2, col="darkblue")
abline(v=CuantilesD[5,1], lty=2, col="brown"); 
abline(v=CuantilesD[5,2], lty=2, col="brown")
legend("topright",legend=c("70%","85%"),
       pch=c(1,2),#3,4,5,6,7,8),
       col=c("brown"))

Muestra pEhExvsCDC53

log2vsCDC53 <- data1$log2samplevsCDC53; head(mean(log2vsCDC53)); head(sd(log2vsCDC53))
## [1] 6.11433
## [1] 2.904448
head(log2vsCDC53,5)
## [1]  8.137224  9.332642 10.134283  7.867231  1.641542
ndata1    <- length(log2vsCDC53)

** Primer histograma**

hist(log2vsCDC53, breaks = nbreaks, col= rainbow(25,0.3), 
     main = 'Log2vsCDC53')

meanlog2vsCDC53 <- mean(log2vsCDC53); head(meanlog2vsCDC53)
## [1] 6.11433
StdDevlog2vsCDC53 <- sd(log2vsCDC53); head(StdDevlog2vsCDC53)
## [1] 2.904448
Normlog2vsCDC53 <- (log2vsCDC53-meanlog2vsCDC53)/StdDevlog2vsCDC53; head(Normlog2vsCDC53)
## [1]  0.6964814  1.1080632  1.3840678  0.6035230 -1.5399785  0.4537713
tst<- Normlog2vsCDC53

Segundo histograma

hist(tst, breaks = nbreaks, col= 1:5, 
     main = 'Normalized Log2vsCDC53',
     xlab='pEhEx1',
     ylab= 'Frequency pEhEx')

Ajustando modelo

fw1<-fitdist(tst, "norm")
plotdist(tst, histo = TRUE, demp = TRUE)

nnorm.f <- fitdist(tst,"norm")
summary(nnorm.f)
## Fitting of the distribution ' norm ' by maximum likelihood 
## Parameters : 
##           estimate Std. Error
## mean -9.490135e-17 0.01447452
## sd    9.998952e-01 0.01023499
## Loglikelihood:  -6770.675   AIC:  13545.35   BIC:  13558.29 
## Correlation matrix:
##      mean sd
## mean    1  0
## sd      0  1
par(mfrow=c(2,2))
denscomp(nnorm.f,legendtext = 'Dist Normal')
qqcomp(nnorm.f,legendtext = 'Dist Normal')
cdfcomp(nnorm.f,legendtext = 'Dist Normal')
ppcomp(nnorm.f,legendtext = 'Dist Normal')

Calculo de cuantiles

probs <- c();
probs[8] = 0.175;  probs[9] = 0.825; 
probs[7] = 0.15;   probs[10] = 0.85;   
probs[6] = 0.125;  probs[11] = 0.875; 
probs[5] = 0.1;    probs[12] = 0.9;    
probs[4] = 0.075;  probs[13] = 0.925; 
probs[3] = 0.05;   probs[14] = 0.95;   
probs[2] = 0.025;  probs[15] = 0.975; 
probs[1] = 0.005;  probs[16] = 0.995;  
CuantilesData <- quantile(tst,prob = probs)
CuantilesModel <- qnorm(probs, mean=0, sd=1)
Cuantilillos <- t(CuantilesModel)
colnames(Cuantilillos) <- c('0.5%','2.5%','5%','7.5%',
                            '10%','12.5%','15%','17.5%',
                            '82.5%','85%','87.5%','90%',
                            '92.5%','95%','97.5%','99.5%')
Cuantilillos <- t(Cuantilillos)
colnames(Cuantilillos) <- c('Cuantiles Ajuste')
print(Cuantilillos)
##       Cuantiles Ajuste
## 0.5%        -2.5758293
## 2.5%        -1.9599640
## 5%          -1.6448536
## 7.5%        -1.4395315
## 10%         -1.2815516
## 12.5%       -1.1503494
## 15%         -1.0364334
## 17.5%       -0.9345893
## 82.5%        0.9345893
## 85%          1.0364334
## 87.5%        1.1503494
## 90%          1.2815516
## 92.5%        1.4395315
## 95%          1.6448536
## 97.5%        1.9599640
## 99.5%        2.5758293
CuantilesA <- matrix(0,8,2)
CuantilesD <- matrix(0,8,2)
colnames(CuantilesA) <- c('LimInf','LimSup')
colnames(CuantilesD) <- c('LimInf','LimSup')
rownames(CuantilesA) <- c('65','70','75','80','85','90','95','99')
rownames(CuantilesD) <- c('65','70','75','80','85','90','95','99')
CuantilesA[1,1] <-CuantilesData[8]; CuantilesA[1,2] <-CuantilesData[9]
CuantilesA[2,1] <-CuantilesData[7]; CuantilesA[2,2] <-CuantilesData[10]
CuantilesA[3,1] <-CuantilesData[6]; CuantilesA[3,2] <-CuantilesData[11]
CuantilesA[4,1] <-CuantilesData[5]; CuantilesA[4,2] <-CuantilesData[12]
CuantilesA[5,1] <-CuantilesData[4]; CuantilesA[5,2] <-CuantilesData[13]
CuantilesA[6,1] <-CuantilesData[3]; CuantilesA[6,2] <-CuantilesData[14]
CuantilesA[7,1] <-CuantilesData[2]; CuantilesA[7,2] <-CuantilesData[15]
CuantilesA[8,1] <-CuantilesData[1]; CuantilesA[8,2] <-CuantilesData[16]
CuantilesD[1,1] <-Cuantilillos[8];  CuantilesD[1,2] <-Cuantilillos[9]
CuantilesD[2,1] <-Cuantilillos[7];  CuantilesD[2,2] <-Cuantilillos[10]
CuantilesD[3,1] <-Cuantilillos[6];  CuantilesD[3,2] <-Cuantilillos[11]
CuantilesD[4,1] <-Cuantilillos[5];  CuantilesD[4,2] <-Cuantilillos[12]
CuantilesD[5,1] <-Cuantilillos[4];  CuantilesD[5,2] <-Cuantilillos[13]
CuantilesD[6,1] <-Cuantilillos[3];  CuantilesD[6,2] <-Cuantilillos[14]
CuantilesD[7,1] <-Cuantilillos[2];  CuantilesD[7,2] <-Cuantilillos[15]
CuantilesD[8,1] <-Cuantilillos[1];  CuantilesD[8,2] <-Cuantilillos[16]
print(CuantilesD)
##        LimInf    LimSup
## 65 -0.9345893 0.9345893
## 70 -1.0364334 1.0364334
## 75 -1.1503494 1.1503494
## 80 -1.2815516 1.2815516
## 85 -1.4395315 1.4395315
## 90 -1.6448536 1.6448536
## 95 -1.9599640 1.9599640
## 99 -2.5758293 2.5758293
print(CuantilesA)
##        LimInf    LimSup
## 65 -0.8305939 0.8018512
## 70 -0.8877013 0.9412276
## 75 -0.9522378 1.1212912
## 80 -1.0264291 1.3220406
## 85 -1.1638210 1.5939827
## 90 -1.2824356 2.0684839
## 95 -1.4385679 2.6057307
## 99 -1.8396440 3.5572717

Histogramas

col_sequence <- rainbow(n = 7, alpha = 0.35, start = 0, end = 1)
par(mfrow=c(2,1))
hist(tst, breaks = nbreaks, col = col_sequence,
     main = 'Normalized Log2vsCDC53 pEhEx - DATA', lty = 9)

abline(v=CuantilesA[1,1], lty=2, col="darkgoldenrod4"); # 65% INFERIOR
abline(v=CuantilesA[1,2], lty=2, col="darkgoldenrod4"); # 65% SUPERIOR
abline(v=CuantilesA[2,1], lty=2, col="darkblue"); # 70% INFERIOR
abline(v=CuantilesA[2,2], lty=2, col="darkblue") # 70% SUPERIOR
abline(v=CuantilesA[3,1], lty=2, col="aquamarine4"); # 75% INFERIOR
abline(v=CuantilesA[3,2], lty=2, col="aquamarine4"); # 75% SUPERIOR
abline(v=CuantilesA[4,1], lty=2, col="green");  # 80% INFERIOR
abline(v=CuantilesA[4,2], lty=2, col="green"); # 80% SUPERIOR
abline(v=CuantilesA[5,1], lty=2, col="brown"); # 85% INFERIOR
abline(v=CuantilesA[5,2], lty=2, col="brown"); # 85% SUPERIOR
abline(v=CuantilesA[6,1], lty=2, col="red");  # 90% INFERIOR
abline(v=CuantilesA[6,2], lty=2, col="red"); # 90% SUPERIOR
abline(v=CuantilesA[7,1], lty=2, col="blue");  # 95% INFERIOR
abline(v=CuantilesA[7,2], lty=2, col="blue"); # 95% SUPERIOR
abline(v=CuantilesA[8,1], lty=2, col="orange");  # 99% INFERIOR
abline(v=CuantilesA[8,2], lty=2, col="orange"); # 99% SUPERIOR
legend("topright",
       legend=c("65%","70%","75%","80%","85%","90%","95%","99%"), 
       pch=c(1,2,3,4,5,6,7,8),
       col=c("darkgoldenrod4","darkblue","aquamarine4",
             "green", "brown","red","blue","orange"))
hist(tst, breaks = nbreaks, col = col_sequence,
     main = 'Normalized Log2vsCDC53   pEhEx - ADJUSTED', lty=9)

abline(v=CuantilesD[1,1], lty=2, col="darkgoldenrod4"); # 65% INFERIOR
abline(v=CuantilesD[1,2], lty=2, col="darkgoldenrod4"); # 65% SUPERIOR
abline(v=CuantilesD[2,1], lty=2, col="darkblue");  # 70% INFERIOR
abline(v=CuantilesD[2,2], lty=2, col="darkblue"); # 70% SUPERIOR
abline(v=CuantilesD[3,1], lty=2, col="aquamarine4");  # 75% INFERIOR
abline(v=CuantilesD[3,2], lty=2, col="aquamarine4"); # 75% SUPERIOR
abline(v=CuantilesD[4,1], lty=2, col="green");  # 80% INFERIOR
abline(v=CuantilesD[4,2], lty=2, col="green"); # 80% SUPERIOR
abline(v=CuantilesD[5,1], lty=2, col="brown");  # 85% INFERIOR
abline(v=CuantilesD[5,2], lty=2, col="brown"); # 85% SUPERIOR
abline(v=CuantilesD[6,1], lty=2, col="red");  # 90% INFERIOR
abline(v=CuantilesD[6,2], lty=2, col="red"); # 90% SUPERIOR
abline(v=CuantilesD[7,1], lty=2, col="blue");  # 95% INFERIOR
abline(v=CuantilesD[7,2], lty=2, col="blue"); # 95% SUPERIOR
abline(v=CuantilesD[8,1], lty=2, col="orange");  # 99% INFERIOR
abline(v=CuantilesD[8,2], lty=2, col="orange"); # 99% SUPERIOR
legend("topright",
       legend=c("65%","70%","75%","80%","85%","90%","95%","99%"), 
       pch=c(1,2,3,4,5,6,7,8),
       col=c("darkgoldenrod4","darkblue","aquamarine4",
             "green", "brown","red","blue","orange"))

Grafica Cuantiles del \(65\%\) y \(80\%\)

par(mfrow=c(2,1))
hist(tst, breaks = nbreaks, col = col_sequence,
     main = 'Normalized Log2vsCDC53  pEhEx - DATA', lty=9)

abline(v=CuantilesA[1,1], lty=2, col="darkgoldenrod4"); # 65% INFERIOR
abline(v=CuantilesA[1,2], lty=2, col="darkgoldenrod4"); # 65% SUPERIOR
abline(v=CuantilesA[4,1], lty=2, col="green");  # 80% INFERIOR
abline(v=CuantilesA[4,2], lty=2, col="green"); # 80% SUPERIOR
legend("topright",legend=c("65%","80%"), 
       pch=c(1,2),col=c("darkgoldenrod4","green"))
hist(tst, breaks = nbreaks, col = col_sequence,
     main = 'Normalized Log2vsCDC51  - ADJUSTED', lty=9)

abline(v=CuantilesD[1,1], lty=2, col="darkgoldenrod4"); # 65% INFERIOR
abline(v=CuantilesD[1,2], lty=2, col="darkgoldenrod4"); # 65% SUPERIOR
abline(v=CuantilesD[4,1], lty=2, col="green");  # 80% INFERIOR
abline(v=CuantilesD[4,2], lty=2, col="green"); # 80% SUPERIOR
legend("topright",legend=c("65%","80%"), 
       pch=c(1,2),col=c("darkgoldenrod4","green"))

Grafica Cuantiles del \(70\%\) y \(85\%\)

par(mfrow=c(2,1))
hist(tst, breaks = nbreaks, col = col_sequence, 
     main = 'Normalized Log2vsCDC53 pEhEx - DATA', lty=9)

abline(v=CuantilesA[2,1], lty=2, col="darkblue"); 
abline(v=CuantilesA[2,2], lty=2, col="darkblue")
abline(v=CuantilesA[5,1], lty=2, col="brown"); 
abline(v=CuantilesA[5,2], lty=2, col="brown")
legend("topright",legend=c("70%","85%"),
       pch=c(1,2),#3,4,5,6,7,8),
       col=c("brown"))
hist(tst, breaks = nbreaks, col = col_sequence,
     main = 'Normalized Log2vsCDC53  pEhEx - ADJUSTED', lty=9)

abline(v=CuantilesD[2,1], lty=2, col="darkblue"); 
abline(v=CuantilesD[2,2], lty=2, col="darkblue")
abline(v=CuantilesD[5,1], lty=2, col="brown"); 
abline(v=CuantilesD[5,2], lty=2, col="brown")
legend("topright",legend=c("70%","85%"),
       pch=c(1,2),#3,4,5,6,7,8),
       col=c("brown"))